Fix ClinVarAlleleParser exceptions when parsing newly introduced CLNSIG=VUS-high|mid values.

Author: julesjacobsen

exomiser-data-genome/src/main/java/org/monarchinitiative/exomiser/data/genome/model/parsers/ClinVarAlleleParser.java

@@ -43,7 +43,12 @@ public class ClinVarAlleleParser extends VcfAlleleParser {
 
     static {
         Map<String, ClinSig> temp = new HashMap<>();
+        // ClinVar just seem to make up whatever as they go along. None of this is documented, just found through errors...
         temp.put("Uncertain_significance", UNCERTAIN_SIGNIFICANCE);
+        temp.put("VUS-high", UNCERTAIN_SIGNIFICANCE);
+        temp.put("VUS-mid", UNCERTAIN_SIGNIFICANCE);
+        temp.put("VUS-low", UNCERTAIN_SIGNIFICANCE);
+        temp.put("VUS", UNCERTAIN_SIGNIFICANCE);
 //        temp.put("Uncertain_significance/Uncertain_risk_allele", UNCERTAIN_SIGNIFICANCE);
         temp.put("Benign", BENIGN);
 //        temp.put("Benign/Likely_benign", BENIGN_OR_LIKELY_BENIGN);
@@ -187,6 +192,7 @@ private ClinSig parseClinSig(String clinsig) {
         clinsig = clinsig.replace(",_low_penetrance", "");
         Set<ClinSig> clinSigs = Arrays.stream(clinsig.split("/"))
                 .map(CLINSIG_MAP::get)
+                .filter(Objects::nonNull)
                 .collect(Collectors.toCollection(() -> EnumSet.noneOf(ClinSig.class)));
 
         if (clinSigs.isEmpty()) {

exomiser-data-genome/src/test/java/org/monarchinitiative/exomiser/data/genome/model/parsers/ClinVarAlleleParserTest.java

@@ -22,11 +22,7 @@
 
 import org.junit.jupiter.api.Disabled;
 import org.junit.jupiter.api.Test;
-import org.monarchinitiative.exomiser.core.genome.dao.ClinVarWhiteListReader;
-import org.monarchinitiative.exomiser.core.model.AlleleProtoAdaptor;
 import org.monarchinitiative.exomiser.core.model.pathogenicity.ClinVarData;
-import org.monarchinitiative.exomiser.core.proto.AlleleProto;
-import org.monarchinitiative.exomiser.data.genome.indexers.AlleleConverter;
 import org.monarchinitiative.exomiser.data.genome.model.Allele;
 
 import java.io.*;
@@ -280,6 +276,29 @@ void clnSigLowPenetrance() {
         assertParseLineEquals(line, List.of(expected));
     }
 
+    /* new fun added in Jan 05, 2026 */
+    @Test
+    void clnSigVusHot() {
+        // variant id 3065236
+        String line = "2\t241684718\t.\tCAACATT\tC\t.\t.\tCLNSIG=Uncertain_significance/VUS-high";
+        Allele expected = new Allele(2, 241684718, "CAACATT", "C");
+        expected.setClinVarData(ClinVarData.builder()
+                .primaryInterpretation(UNCERTAIN_SIGNIFICANCE)
+                .build());
+        assertParseLineEquals(line, List.of(expected));
+    }
+
+    // 9	134164522	4688033	C	T	.	.	ALLELEID=4799506;CLNDISDB=.;CLNDN=See_cases;CLNHGVS=NC_000009.12:g.134164522C>T;CLNREVSTAT=no_assertion_criteria_provided;CLNSIG=VUS-mid;CLNSIGSCV=SCV007334818;CLNVC=single_nucleotide_variant;CLNVCSO=SO:0001483;GENEINFO=RNU6ATAC:100151684;MC=SO:0001619|non-coding_transcript_variant;ORIGIN=64
+    @Test
+    void clnSigJustVusMid() {
+        // variant id 4688033 RNU6TAC
+        String line = "9\t134164522\t.\tC\tT\t.\t.\tCLNSIG=VUS-mid";
+        Allele expected = new Allele(9, 134164522, "C", "T");
+        expected.setClinVarData(ClinVarData.builder()
+                .primaryInterpretation(UNCERTAIN_SIGNIFICANCE)
+                .build());
+        assertParseLineEquals(line, List.of(expected));
+    }
     @Test
     void conflictingInterpretationCounts() {
         String line = "1\t94051698\t7879\tC\tG\t.\t.\tCLNREVSTAT=criteria_provided,_conflicting_classifications;CLNSIG=Conflicting_classifications_of_pathogenicity;CLNSIGCONF=Pathogenic(19)|Likely_pathogenic(4)|Pathogenic,_low_penetrance(1)|Uncertain_significance(1);RS=1660844326";